Fingerprint matching using an orientation-based minutia descriptor

We introduce a novel fingerprint representation scheme that relies on describing the orientation field of the fingerprint pattern with respect to each minutia detail. This representation allows the derivation of a similarity function between minutiae that is used to identify corresponding features and evaluate the resemblance between two fingerprint impressions. A fingerprint matching algorithm, based on the proposed representation, is developed and tested with a series of experiments conducted on two public domain collections of fingerprint images. The results reveal that our method can achieve good performance on these data collections and that it outperforms other alternative approaches implemented for comparison.